Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +103 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 330,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.6287968158721924,
|
| 14 |
+
"learning_rate": 9.783837236868609e-05,
|
| 15 |
+
"loss": 2.0146,
|
| 16 |
+
"step": 33
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 1.897132158279419,
|
| 21 |
+
"learning_rate": 9.100305426420956e-05,
|
| 22 |
+
"loss": 0.8409,
|
| 23 |
+
"step": 66
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 2.1679365634918213,
|
| 28 |
+
"learning_rate": 8.015407152327448e-05,
|
| 29 |
+
"loss": 0.5425,
|
| 30 |
+
"step": 99
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 2.982478380203247,
|
| 35 |
+
"learning_rate": 6.635339816587109e-05,
|
| 36 |
+
"loss": 0.3347,
|
| 37 |
+
"step": 132
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 2.2915990352630615,
|
| 42 |
+
"learning_rate": 5.095194025516733e-05,
|
| 43 |
+
"loss": 0.2133,
|
| 44 |
+
"step": 165
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 2.5713918209075928,
|
| 49 |
+
"learning_rate": 3.545729979973005e-05,
|
| 50 |
+
"loss": 0.1354,
|
| 51 |
+
"step": 198
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 1.6528334617614746,
|
| 56 |
+
"learning_rate": 2.1386200164845526e-05,
|
| 57 |
+
"loss": 0.0824,
|
| 58 |
+
"step": 231
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 1.591257095336914,
|
| 63 |
+
"learning_rate": 1.0116018621892237e-05,
|
| 64 |
+
"loss": 0.0583,
|
| 65 |
+
"step": 264
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 0.5333567261695862,
|
| 70 |
+
"learning_rate": 2.7499590642665774e-06,
|
| 71 |
+
"loss": 0.0476,
|
| 72 |
+
"step": 297
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 0.3626488447189331,
|
| 77 |
+
"learning_rate": 9.06272382371065e-09,
|
| 78 |
+
"loss": 0.0434,
|
| 79 |
+
"step": 330
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"logging_steps": 500,
|
| 83 |
+
"max_steps": 330,
|
| 84 |
+
"num_input_tokens_seen": 0,
|
| 85 |
+
"num_train_epochs": 10,
|
| 86 |
+
"save_steps": 500,
|
| 87 |
+
"stateful_callbacks": {
|
| 88 |
+
"TrainerControl": {
|
| 89 |
+
"args": {
|
| 90 |
+
"should_epoch_stop": false,
|
| 91 |
+
"should_evaluate": false,
|
| 92 |
+
"should_log": false,
|
| 93 |
+
"should_save": true,
|
| 94 |
+
"should_training_stop": true
|
| 95 |
+
},
|
| 96 |
+
"attributes": {}
|
| 97 |
+
}
|
| 98 |
+
},
|
| 99 |
+
"total_flos": 920382499768320.0,
|
| 100 |
+
"train_batch_size": 1,
|
| 101 |
+
"trial_name": null,
|
| 102 |
+
"trial_params": null
|
| 103 |
+
}
|